US 12,283,100 B2
Image classification in a sequence of frames
Orlando Miguel Pires Dos Reis Moreira, Eindhoven (NL); and Louis Rouillard-Odera, Paris (FR)
Assigned to Snap Inc., Santa Monica, CA (US)
Appl. No. 17/630,250
Filed by Snap Inc., Santa Monica, CA (US)
PCT Filed Sep. 4, 2020, PCT No. PCT/EP2020/074845
§ 371(c)(1), (2) Date Jan. 26, 2022,
PCT Pub. No. WO2021/044021, PCT Pub. Date Mar. 11, 2021.
Claims priority of application No. 19195984 (EP), filed on Sep. 6, 2019.
Prior Publication US 2022/0254135 A1, Aug. 11, 2022
Int. Cl. G06V 20/40 (2022.01); G06T 3/40 (2024.01); G06V 10/25 (2022.01); G06V 10/74 (2022.01); G06V 10/762 (2022.01); G06V 10/764 (2022.01); G06V 10/80 (2022.01)
CPC G06V 20/40 (2022.01) [G06T 3/40 (2013.01); G06V 10/25 (2022.01); G06V 10/74 (2022.01); G06V 10/763 (2022.01); G06V 10/764 (2022.01); G06V 10/80 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for classifying image content in a sequence of image frames, the method comprising:
converting frame image data, representing an appearance of image content of the image frames, into frame event data defining a set of events, wherein the converting comprises determining, for each event of the set of events, a set of event parameters including positional coordinates corresponding to a location of a respective pixel in the image frames used to derive the event, and further including a respective value indicating at least one of an amount of change of the respective pixel or a polarity of the change based on comparison of values of the respective pixel between different image frames in the sequence of image frames;
processing the set of event parameters of the frame event data to determine an event-based region of interest in the sequence of image frames; and
calculating at least one classification based on an intersection of the event-based region of interest with the frame image data of an image frame in the sequence.